Quick links: 
[[https://intranet.fel.cvut.cz/cz/education/rozvrhy-ng.B232/public/html/predmety/61/70/p6170206.html | Schedule]] | 
[[https://cw.felk.cvut.cz/forum/forum-1874.html|Forum]] | 
[[https://cw.felk.cvut.cz/brute/teacher/course/1595| BRUTE]] | 
[[https://cw.fel.cvut.cz/b232/courses/bev033dle/lectures | Lectures]] |


===== Labs and Seminars =====
Two types of labs (tutorials) will be proposed for the course (alternating):
  * practical labs in which students will implement selected methods discussed in the course and experiment with them
  * theoretical labs in which students will discuss solutions of theoretical assignments (posted 1 week before the class)

==== Teachers: ====
  * Boris Flach
  * Alexander Shekhovtsov
  * Jan Šochman
  * Nikolaos Efthymiadis
  * Vladan Stojnić

==== Schedule  ====
(contents will be updated)
^ Date ^ Topic ^ Teacher ^ Reading ^
| 22.02.2024 ^ [[courses:bev033dle:labs:Lab0_ddescent:start | Lab 1: Preparations, Double Descent ]] ^ AS | {{ https://www.cs.toronto.edu/~rgrosse/courses/csc2541_2022/readings/L01_intro.pdf | NNTD lecture 1}} (except 2.3, 5) |
| 29.02.2024 ^ {{:courses:bev033dle:labs:sem-neurons-nets.pdf|Seminar 1 (lecture 1)}} ^ BF |
| 07.03.2024 ^ [[courses:bev033dle:labs:Lab1_backprop:start | Lab 2: Backpropagation, Computational graph ]] ^ AS|
| 14.03.2024 ^ {{:courses:bev033dle:labs:sem-nets-backprop.pdf|Seminar 2 (lectures 2,3)}} ^ JS |
| 21.03.2024 ^ [[courses:bev033dle:labs:Lab2_finetune:start | Lab 3: CNN Fine-tuning]] ^ NE |
| 28.03.2024 ^ {{:courses:bev033dle:labs:sem-sgd-cnn.pdf|Seminar 3 (lectures 4,5)}} ^ JS |
| 04.04.2024 ^ [[courses:bev033dle:labs:Lab3_fromscratch:start | Lab 4: From Scratch: Initialization & regularization]] ^ JS|
| 11.04.2024 ^ {{ :courses:bev033dle:labs:sem-init-reg.pdf | Seminar 4 (lectures 6,7)}} ^ AS |
| 18.04.2024 ^ [[courses:bev033dle:labs:Lab4_visualization:start | Lab 5: CNN visualization & adversarial patterns]] ^ BF |
| 25.04.2024 ^ {{ :courses:bev033dle:labs:sem-adapt-advers.pdf | Seminar 5 (lectures 8,9)}} ^ AS|
| 02.05.2024 ^ [[courses:bev033dle:labs:Lab6_metric:start | Lab 6: Metric learning ]] ^JS |
| 09.05.2023 | --- no class --- | |
| 16.05.2024 ^ [[courses:bev033dle:labs:Lab7_VAE:start | Lab 7: VAE ]] ^ BF|
| 23.05.2024 ^ Seminar 6 (lectures 10,11) ^AS |


/**
:courses:bev033dle:labs:sem-nets-backprop.pdf
:courses:bev033dle:labs:sem-sgd-cnn.pdf
**/

/**
| 25.04.2024 ^ {{ :courses:bev033dle:labs:sem-adapt-advers.pdf | Seminar 5 (lectures 8,9)}} ^ AS|
| 02.05.2024 ^ [[courses:bev033dle:labs:Lab6_metric:start | Lab 6: Metric learning ]] ^JS |
| 09.05.2023 | --- no class --- | |
| 16.05.2024 ^ {{ :courses:bev033dle:labs:sem-metric-kl-svi.pdf | Seminar 6 (lectures 10,11) }} ^AS |
| 23.05.2024 ^ [[courses:bev033dle:labs:Lab7_VAE:start | Lab 7: VAE (bonus)]] ^ BF|
**/
==== Seminars ====
The seminar assignments are published 1 week in advance before the seminar. You are expected to prepare for it at home. We discuss the problems and solutions in the class. You are not required to submit you solutions, but if you solved a problem you will be invited to present it in the class. Seminars are not scored by points but they are important for gaining technical understanding, which will be finally evaluated in the written exam.


Examples of problems with solutions: {{ :courses:bev033dle:labs:examples.pdf |}} (to be updated)

==== Labs ====

The solutions of the practical labs have to be submitted using the [[http://cw.felk.cvut.cz/upload/|upload system]]
  * Your task will be to program a solution of the assigned problems. You have to hand out your code and a report. The report has to contain only answers to the assignments (nothing else). 
  * The programming language is Python/PyTorch.
  * The deadline for submitting your solutions will be 2 weeks after the date of assignment. This is a soft deadline, if you still submit within 3 weeks you get a deduction of 3 points from the maximum 10 (for the first lab deduction of 2 points from the maximum 5). End of the week 3 is a hard deadline.
  * Not submitting a lab is equivalent to getting 0 points. You need at least of 50% of total lab points to pass.



==== Submission Regulations ====

You may choose from the following submission variants:

  - Report in pdf and Python source code
  - Annotated Jupyter notebook with inline results and Python source code if applicable

Please do not submit data and any other redundant files.
Sharing code that is not a required part of the assignment is permitted, for example additional visualization code or test cases for debugging.